Ego-vision-based navigation in cluttered environments is crucial for mobile systems, particularly agile quadrotors. While learning-based methods have shown promise recently, head-to-head comparisons with cutting-edge optimization-based approaches are scarce, leaving open the question of where and to what extent they truly excel. In this paper, we introduce FlightBench, the first comprehensive benchmark that implements various learning-based methods for ego-vision-based navigation and evaluates them against mainstream optimization-based baselines using a broad set of performance metrics. Additionally, we develop a suite of criteria to assess scenario difficulty and design test cases that span different levels of difficulty based on these criteria. Our results show that while learning-based methods excel in high-speed flight and faster inference, they struggle with challenging scenarios like sharp corners or view occlusion. Analytical experiments validate the correlation between our difficulty criteria and flight performance. We hope this benchmark and these criteria will drive future advancements in learning-based navigation for ego-vision quadrotors. The source code and documentation is available at \url{https://github.com/thu-uav/FlightBench}.

翻译：在杂乱环境中基于第一人称视觉的导航对移动系统（尤其是敏捷四旋翼无人机）至关重要。尽管基于学习的方法近期展现出潜力，但其与前沿优化方法的直接对比研究仍显不足，这些方法在何种场景及何种程度上真正具有优势尚不明确。本文提出首个综合性基准测试平台FlightBench，该平台实现了多种基于第一人称视觉导航的学习方法，并采用多维性能指标将其与主流优化基线方法进行系统评估。此外，我们开发了一套用于评估场景难度的标准体系，并依据该体系设计了覆盖不同难度等级的测试用例。实验结果表明：基于学习的方法在高速飞行与快速推理方面表现优异，但在急转弯或视野遮挡等挑战性场景中仍存在局限。分析性实验验证了所提难度标准与飞行性能之间的相关性。我们期望该基准测试平台及难度标准能推动第一人称视觉无人机导航学习方法的未来发展。源代码及文档详见 \url{https://github.com/thu-uav/FlightBench}。